Detection and biomechanical analysis of human posture embedded electronic system based on D-H matrix method

This paper briefly describes the similarities and differences of the mainstream models of deep learning target detection box, analyzes the characteristics and advantages of Mask RCNN, a universal target detection box, and focuses on the application of Mask RCNN in human posture detection in multi- person human posture task. Through the analysis, it is considered that the advantage of Mask RCNN in multi-person human posture detection task is the accuracy, while the bottleneck is the detection speed. To solve this problem, an optimization of Mask RCNN model based on MobileNet was proposed to accelerate the inference calculation speed of Mask RCNN. At the same time, in order to further improve the detection accuracy of Mask RCNN, a method of using pixel segmentation results to assist the detection of human body key points is proposed. Experimental results show that compared with the original algorithm, it improves the reasoning speed and reduces the false detection rate caused by the environment.

With the continuous improvement of intelligence in the coal industry, intelligent video analysis and judgment of dangerous behaviors that have occurred can no longer meet the needs of human posture detection in underground mines. In this paper, a human posture detection algorithm based on MMPose is proposed to determine the body posture of personnel under the mine at different times, in order to provide effective information for standardizing miner operations, disaster early warning, and accident rescue. The algorithm is based on MMPose technology, which improves and optimizes the existing shortcomings, facilitating the determination of the body posture of underground personnel at different times, and solving the low accuracy issues of occlusion image detection, multi-person image detection, and dark environment detection. The designed algorithm achieves labeling of 17 key points such as eyes, nose, ears, shoulders, elbows, hands, legs, knees, and feet, and can detect various postures such as standing upright, standing sideways, sitting, squatting, and walking. Experiments have shown that this algorithm has a high accuracy in human posture detection and prediction, and can better mark the key points of the human body for occluded images, multi-person images, and dark environments, meeting the real-time requirements of underground personnel posture detection.

This paper describes a video surveillance system capable of recognizing human postures from video sequences. The system comprises of two key modules: human detection and posture classification. In the module of human detection, human blobs are extracted by the technique of background subtraction. An adaptive background model is employed to characterize the dynamics and complexity of outdoor scenes based on the mixture of Gaussians. In order to formulate the variations of human postures, pseudo 2D hidden Markov models (P2DHMM) is employed for representing and recognizing human postures based on its '2-D elastic matching' property. It is trained to differentiate human postures and tolerate the variations of the same human posture using embedded Viterbi and segmental K means algorithms. In the classification of human postures, observation sequence is extracted from current image frame. The probabilities of observation sequence corresponding to each P2DHMM model are computed by doubly embedded Viterbi optimization, and human blob is classified as the human posture with the highest likelihood.

Human posture detection is easily affected by the external environment, resulting in blurred results of limb feature extraction. In order to improve the accuracy and speed of human motion detection, this paper proposes a deep learning-based motion detection method in competitive sports training. The double parallel convolution network algorithm in the depth learning algorithm is used to process the collected action information, extract the body action features, and greatly reduce the operation scale; With the help of the theory of motion mechanics, the mechanical parameters in the motion process are calculated to eliminate outliers and reduce feature dimensions; With the help of motion inertial sensors and joint degrees of freedom, the limb motion detection results are obtained. The experimental results show that the average recognition rate of the method for different motion actions is 99.5%, and the average detection time is 148 ms, with good application performance.

The current traditional human pose detection methods mainly acquire the pose data collected by sensors and realize the pose discrimination by edge computing decision unit, which leads to poor detection effect due to the lack of fusion of sensor data. In this regard, a high difficulty yoga body pose detection method based on data fusion is proposed. Complementary filtering, Kalman filtering and adaptive Kalman filtering methods are used to fuse sensor data for pose prediction, and a skeleton extraction model is constructed to build a multilayer perceptron network architecture to achieve the detection of difficult yoga asana poses. In the experiments, the proposed human posture detection method is validated. The analysis of the experimental results shows that the proposed method has a high comprehensive evaluation index and excellent detection performance when used for the detection of difficult yoga asana postures.

We investigate the influence of two attitude estimation methods for human posture detection. In the context of ADL (i.e. Activities of Daily Living) we analyze inertial sensors to reveal uncomfortable situations. Quantifying postures such as standing up, walking, lying down or sitting may feature people autonomy and well being. We report comparisons between two main attitude estimation strategies. Our experimental protocol uses a precise ground truth obtained from two annotators. The dataset involves 9 participants and provides 50 various data sequences. We discuss the obtained promising results, analyze advantages and limits when using attitude estimation in this context.

Human Posture detection using Deep learning techniques are widely useful in many areas like face recognition, video games, virtual reality, animations and many varieties of physical training. In this work, we are applying deep learning techniques like convolution neural networks (CNN) in the field of Yoga. It is a form of physical exercise which helps to improve both the physical and mental state of humans. There are different styles of yoga that combine physical poses, breathing techniques, and meditation or relaxation to promote mental and physical well-being. We have used a dataset which consists of five different yoga poses for training the model and evaluating the prediction accuracy of the model. The system recognizes a yoga pose from a given image using a CNN model and three CNN architectures such as VGG16, VGG19 and MobileNet. In comparison, among the four, VGG19 model achieved an accuracy of 99.49% which is higher than the other models.

Existing human motion detection technologies have problems such as insufficient accuracy and poor real-time performance, which makes it difficult to meet the needs of health management. This paper proposes a human motion posture detection and humanized calculation method based on multi-sensor fusion and LSTM. This paper first deploys IMU sensors at key parts of the human body, and uses visual sensors to capture the three-dimensional posture information of human motion, and obtains physiological data such as heart rate and number of steps through wearable devices such as smart bracelets. Secondly, the IMU data is denoised and calibrated to eliminate sensor errors. Next, the fused data is trained using a long short-term memory network (LSTM). The rationality of the motion posture is then analyzed, and the user's exercise intensity and health status are evaluated based on the motion data and physiological data. In terms of posture recognition accuracy, the average value of this method is 92.61 %. In terms of abnormal posture detection rate, the detection rate of some data points of this method is close to 100%. At the same time, the maximum recognition time of this method is only 789 milliseconds, and the minimum recognition time is as low as 503 milliseconds, which is better than the traditional method. The optimized human motion posture detection and humanized calculation method proposed in this paper realizes high-precision detection of human motion and intelligent health management through multi-source data fusion, LSTM construction, human kinematics analysis and personalized health assessment.

In order to make the elderly care service system intelligent, this paper proposes a human posture recognition algorithm based on big data analysis and artificial intelligence technology. The algorithm framework includes three parts: human target detection, human posture estimation and human action recognition. Firstly, this paper adopts the obscured human body detection algorithm based on the mixed attention mechanism to detect the human bounding box. Then, to solve the problem that the detected human bounding box may have inaccurate positioning leading to the human body position deviation, the space transformation network is used to affine the coordinates of the human bounding box to correct its position. Finally, the stacked hourglass network is used to predict the joints of the detected human body, so as to realize the recognition of human posture. In this paper, the algorithm is trained and tested on the open pedestrian test set. The experimental results show that the algorithm in this paper can effectively and correctly estimate the visible parts of human posture, and reduce the influence of obstacle occlusion on human posture estimation and human fall detection. The evaluation index of human posture recognition (Kps AP) reached 68.7%, indicating that the posture recognition algorithm proposed in this paper can realize the rapid recognition and estimation of human posture without shelter, and the algorithm can complete the fall recognition of the elderly in the elderly service system, and can effectively prevent the elderly from falling after the subsequent big data statistics and analysis of the elderly's posture. It has good practicability.

With the continuous development of computer networks and the continuous popularization of computer network technology, image detection technology has gained a lot of room for development with the help of the development of image processing technology, and has also been greatly improved in a period of development. When people carry out geotechnical engineering construction, the stability of the slope is related to the safety and construction effect of the entire project. In the specific operation process, researchers usually use appropriate calculation methods to calculate various parameters in engineering construction, and use calculations to specifically determine the stability of highway slopes. In order to improve the safety of geotechnical engineering construction and the stability of highway slopes, this article selects the parameters involved in the slope stability analysis method for analysis, and establishes an equation for reliability analysis during the analysis. By comparing the analysis results of other methods, the researchers believe that the limit equation set in this article can improve the reliability of slope stability analysis. This article also designs a method of human motion image detection, which specifically studies the human motion posture, and uses the characteristics of the skeleton point image and the Euclidean distance to accurately recognize the human motion.

Fusing object detection techniques and stochastic variational inference, we proposed a new scheme for lightweight neural network models, which could simultaneously reduce model sizes and raise the inference speed. This technique was then applied in fast human posture identification. The integer-arithmetic-only algorithm and the feature pyramid network were adopted to reduce the computational complexity in training and to capture features of small objects, respectively. Features of sequential human motion frames (i.e., the centroid coordinates of bounding boxes) were extracted by the self-attention mechanism. With the techniques of Bayesian neural network and stochastic variational inference, human postures could be promptly classified by fast resolving of the Gaussian mixture model for human posture classification. The model took instant centroid features as inputs and indicated possible human postures in the probabilistic maps. Our model had better overall performance than the baseline model ResNet in mean average precision (32.5 vs. 34.6), inference speed (27 vs. 48 milliseconds), and model size (46.2 vs. 227.8 MB). The model could also alert a suspected human falling event about 0.66 s in advance.

A new scheme for human posture recognition is proposed based on analysis of key body parts. Utilizing a time-of-flight depth camera, a pulse coupled neural network (PCNN) is employed to detect a moving human in cluttered background. In the posture recognition phase, a hierarchical decision tree is designed for classification of body parts so that the 3D coordinate of the key points of the detected human body can be determined. The features described in each individual layer of the tree can be chained as hierarchical searching indices for retrieval procedure to drastically improve the efficiency of template matching in contrast to conventional shape-context method. Experimental results show that the proposed scheme gives competitive performance as compared with the state-of-the-art counterparts.

Experimental study of through-wall human detection using ultra wideband radar sensors

The main concern of human detection using computer vision is to correctly identify people in an image and video. Human detection has been a topic of intensive study over the last decade. YOLO being single stage algorithms happen to offer better speed than two stage algorithms hence making them a better choice for real time object detection. This strategy has the benefit of offering a comprehensive study of contemporary human detection techniques as well as a manual for selecting the best ones for actual applications. In addition, Real-time human detection and occlusion issues are also looked at. In this paper, experimentation is done on real time image to verify the performance of different models of YOLO family i.e YOLOv3, YOLOv4 and YOLOv5. The experiment shows that YOLOv5 is best performer in terms of mAP with precision of 0.84 while YOLO v3 is the fastest but with a slightly less precision of 0.71. The mAP of the three algorithms were 0.86, 0.89 and 0.91 respectively.

With the development of the artificial intelligence field, automatic drive, and machine learning, both did well in their field. Human posture estimation could help people in many cases, as an imitation of the human body, entertainment, sports, and other field have had some achievement, also shows the importance of human posture estimation for the future. In 2013, Toshev introduced Deep Pose into human posture estimation, and the study of human body posture estimation began to shift from traditional methods to Deep learning. CNN was firstly proposed to be applied to the detection of human joints and transform the estimation of human body posture into the regression problem of joints. Secondly, CPM mainly uses Heatmap to represent joints' position and position constraint relationship, which can fully consider the spatial position relationship between various joints. Then in the process of top to bottom and bottom to top in Hourglass, through convolution and pooling, the image's resolution is adjusted to the best, and the information of the image is integrated. CPN also uses the top-down method to detect the body frame first and detect the human body nodes in the body frame. RefineNet can correct the results with large errors. HRNET is the follow-up to Simple Baseline, which enables multi-scale fusion through information exchange across resolution subnetworks. We discussed a lot about human posture. Deep learning has led to the rapid development of academy and technology. The development of technology will improve our future analysis on human detection data, for example, detect our daily walking state, or in different occasions through images and other data to analyze the characteristics of the human posture. This will help us develop in the future, which will have a crucial impact on our development.